Downloads · 30 days
37
0% of all-time downloads
legal-romanian-roberta-base
joelniklaus/legal-romanian-roberta-base
legal-romanian-roberta-base is a fill-mask model from joelniklaus. Use it when you need the model to fill a missing word. It is set up for transformers.
should probably proofread and complete it, then remove this comment. --
All-time downloads
381K
Public
Repo size
5.8 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin443 MB · 100%
At a glance
- Task
- Fill-Mask
- Library
- transformers
- Model type
- roberta
- Access
- Public
- Created
- Feb 6, 2023
- Updated
- Feb 13, 2023
- SHA
- b24debf0
Try a prompt
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
legal-romanian-roberta-base
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4841
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: tpu
- num_devices: 8
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- total_eval_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- training_steps: 200000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7902 | 2.02 | 50000 | 0.6112 |
| 0.7387 | 4.03 | 100000 | 0.5347 |
| 0.6488 | 6.05 | 150000 | 0.5026 |
| 0.6702 | 8.07 | 200000 | 0.4841 |
Framework versions
- Transformers 4.20.1
- Pytorch 1.12.0+cu102
- Datasets 2.9.0
- Tokenizers 0.12.0
- Task
- Fill-Mask
- Library
- transformers
- Type
- roberta
- Created
- Feb 6, 2023
- Updated
- Feb 13, 2023